Kandinsky Image Generation with ControlNet Conditioning
This model costs approximately $0.011 to run on Replicate, or 90 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.
This model runs on Nvidia A100 (80GB) GPU hardware. Predictions typically complete within 9 seconds. The predict time for this model varies significantly based on the inputs.
Model card: https://huggingface.co/kandinsky-community/kandinsky-2-2-controlnet-depth
img2img controlnet keeps a lot more details from the original image compared to the text2img controller.
Hight and weight of the output should be set similar to the input image.
